No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from RedHatAI/gemma-4-26B-A4B-it-speculator.eagle3
All models by RedHatAI →This is a preliminary model release, we will continue to train the model and improve the acceptance rates in the next few days.
This is a speculator model designed for use with google/gemma-4-26B-A4B-it, based on the EAGLE-3 speculative decoding algorithm.
It was trained using the Speculators library on a combination of the Magpie-Align/Magpie-Llama-3.1-Pro-300K-Filtered dataset and the train_sft split of the HuggingFaceH4/ultrachat_200k dataset. Training data used Magpie + UltraChat with responses from the gemma-4-31B-it model (no reasoning).
This model should be used with the google/gemma-4-26B-A4B-it chat template, specifically through the /chat/completions endpoint.
UPDATE: Now supported on vllm-main!
Model / run:
vLLM: UPDATE: Now supported on vllm-main!
Training data: Magpie + UltraChat; responses from the gemma 4 31B it model (no reasoning).
vllm serve google/gemma-4-26B-A4B-it \ --tensor-parallel-size 2 \ --speculative-config '{ "model": "RedHatAI/gemma-4-26B-A4B-it-speculator.eagle3", "num_speculative_tokens": 3, "method": "eagle3" }' \ --max-num-seqs 64 \